8 citations · 13 across the 17 of their papers we have counts for
13 papers · 1 filter
Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations
Salvatore Greco, Hainiu Xu, Jacopo Domenicucci +2
LLMs are increasingly deployed as Artificial Moral Advisors (AMA) in a variety of contexts: what kind of conversational patterns should they display? In this paper, we study how AM…
When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment
Hanqi Yan, Hainiu Xu, Siya Qi +2
With the growing accessibility and wide adoption of large language models, concerns about their safety and alignment with human values have become paramount. In this paper, we iden…
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
Runcong Zhao, Qinglin Zhu, Hainiu Xu +3
Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming an…
EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphs
Bohao Yang, Hainiu Xu, Jinhua Du +3
A compelling portrayal of characters is essential to the success of narrative writing. For readers, appreciating a character's traits requires the ability to infer their evolving b…
Modeling Subjectivity in Cognitive Appraisal with Language Models
Yuxiang Zhou, Hainiu Xu, Desmond C. Ong +3
As the utilization of language models in interdisciplinary, human-centered studies grow, expectations of their capabilities continue to evolve. Beyond excelling at conventional tas…
EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States
Hainiu Xu, Siya Qi, Jiazheng Li +4
Theory-of-Mind (ToM), the ability to infer others' perceptions and mental states, is fundamental to human interaction but remains challenging for Large Language Models (LLMs). Whil…
RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors
Liam Dugan, Alyssa Hwang, Filip Trhlik +5
Many commercial and open-source models claim to detect machine-generated text with extremely high accuracy (99% or more). However, very few of these detectors are evaluated on shar…
Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring
Jiazheng Li, Hainiu Xu, Zhaoyue Sun +4
Generating rationales that justify scoring decisions has been a promising way to facilitate explainability in automated scoring systems. However, existing methods do not match the…
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives
Runcong Zhao, Qinglin Zhu, Hainiu Xu +4
Existing datasets for narrative understanding often fail to represent the complexity and uncertainty of relationships in real-life social scenarios. To address this gap, we introdu…
Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
Xinyu Wang, Hainiu Xu, Lin Gui +1
Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interp…
OpenPI2.0: An Improved Dataset for Entity Tracking in Texts
Li Zhang, Hainiu Xu, Abhinav Kommula +2
Much text describes a changing world (e.g., procedures, stories, newswires), and understanding them requires tracking how entities change. An earlier dataset, OpenPI, provided crow…
Exploring the Curious Case of Code Prompts
Li Zhang, Liam Dugan, Hainiu Xu +1
Recent work has shown that prompting language models with code-like representations of natural language leads to performance improvements on structured reasoning tasks. However, su…
Causal Reasoning of Entities and Events in Procedural Texts
Li Zhang, Hainiu Xu, Yue Yang +4
Entities and events are crucial to natural language reasoning and common in procedural texts. Existing work has focused either exclusively on entity state tracking (e.g., whether a…